CVSS 4.0
5.5 mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:PMedium (5.5) in vllm vllm. EPSS 0.7% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.27.0.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:PCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hvllm (PyPI): fixed in 0.27.0Explain CVE-2026-103241 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-103241?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-103241?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-103241 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.
From the NVD's CPE matches.
| Product | Affected |
|---|---|
| vllm:vllm | through 0.26.0 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| PYSEC-2026-4186 | PyPI | vllm | <0.27.0 | 0.27.0 |
Red Hat rates this Important.
An important impact denial of service flaw was found in the upstream vLLM project, in the Rust-based Gemma4UnifiedParser component (rust/src/parser/src/unified/gemma4.rs). The parser implements a hand-written recursive grammar without a recursion depth limit, so crafted input containing deeply nested structures, such as nested tool-call arguments in model output, drives unbounded recursion that exhausts a worker thread's stack and terminates the vLLM process. A remote attacker able to submit such manipulated input can cause the model-serving process to become unresponsive or crash, disrupting service for legitimate users; confidentiality and integrity are not affected. Multiple Red Hat AI products ship vulnerable versions of vLLM and are affected by this flaw.
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
| Product | Package | State | Advisory |
|---|---|---|---|
| Red Hat AI Inference Server | rhaii-fast/vllm-cpu-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaii-fast/vllm-cuda-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaii-fast/vllm-gaudi-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaii-fast/vllm-neuron-rhel9 | Will not fix | |
| Red Hat AI Inference Server | rhaii-fast/vllm-omni-cuda-rhel9 | Will not fix | |
| Red Hat AI Inference Server | rhaii-fast/vllm-rocm-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaii-fast/vllm-spyre-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaii-fast/vllm-tpu-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaii/vllm-cpu-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaii/vllm-cuda-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaii/vllm-gaudi-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaii/vllm-neuron-rhel9 | Will not fix | |
| Red Hat AI Inference Server | rhaii/vllm-rocm-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaii/vllm-spyre-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaii/vllm-tpu-rhel9 | Will not fix | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-aws-cuda-rhel9 | Affected | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-cuda-rhel9 | Affected | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-rocm-rhel9 | Affected | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-cuda-rhel9 | Affected | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-gaudi-rhel9 | Affected | |
| 12 more in the JSON and on Red Hat's page. | |||
Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-103241.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.